Triple
T8996158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy McGivern |
E214917
|
entity |
| Predicate | sharesNationalityWith |
P49688
|
FINISHED |
| Object | Linfield FC supporters in Northern Ireland |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Linfield FC supporters in Northern Ireland | Statement: [Roy McGivern, sharesNationalityWith, Linfield FC supporters in Northern Ireland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesNationalityWith Context triple: [Roy McGivern, sharesNationalityWith, Linfield FC supporters in Northern Ireland]
-
A.
sharesCountryWith
chosen
Indicates that two entities are located in, originate from, or are otherwise associated with the same country.
-
B.
associatedWithNationality
Indicates that one entity has a connection or affiliation with the nationality of another entity.
-
C.
includedNationality
Indicates that one entity’s set of nationalities contains or encompasses the nationality of another entity.
-
D.
nationalityOfPersonReferredTo
Indicates that one entity is the country or nationality associated with the person referenced by the other entity.
-
E.
nationalityInText
Indicates that a person's nationality is mentioned or specified within a given text.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca83a05c608190bdfdbdb25e994b39 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc68df33c48190a5017426e59c0bc4 |
completed | April 1, 2026, 12:37 a.m. |
| PD | Predicate disambiguation | batch_69cc5edba0f88190b97401636a076d7a |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:04 p.m.